Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    nouns and terms that indicate specialization or expertise in a specific field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _kw
    -0.17
     fflush
    -0.17
     Pear
    -0.16
    imas
    -0.15
    ahoo
    -0.14
    autos
    -0.14
    pies
    -0.14
    idot
    -0.14
    amac
    -0.14
    cke
    -0.14
    POSITIVE LOGITS
     glu
    0.32
     fragmentation
    0.27
     sea
    0.24
     pom
    0.23
     Pom
    0.23
     Bj
    0.23
     unint
    0.23
     color
    0.23
     PDF
    0.22
     twist
    0.22
    Act Density 0.005%

    No Known Activations